车辆特征提取(小波轮廓检测和Moracev焦点检测).zip资源matlab opencv运动目标检测程序资料

%extracting objects提取目biao im=imread('17.bmp'); I=rgb2gray(im); im1=medfilt2(I,[2 2]); %Median filtering the image to remove noise% BW=edge(im1,'sobel'); %finding edges [imx,imy]=size(BW); msk=[ 1 1 1 ; 1 1 1 ; 1 1 1 ; ]; B=conv2(double(BW),double(msk)); %Smoothing image to reduce the number of connected components L = bwlabel(B,8);% Calculating connected components mx=max(max(L)) % There will be mx connected components.Here U can give a value between 1 and mx for L or in a loop you can extract all connected components % If you are using the attached car image, by giving 17,18,19,22,27,28 to L you can extract the number plate completely. [r,c] = find(L==17); rc = [r c]; [sx sy]=size(rc); n1=zeros(imx,imy); for i=2:sx x1=rc(i,1); y1=rc(i,2); n1(x1,y1)=255; end % Storing the extracted image in an array figure,imshow(im); figure,imshow(im1); figure,imshow(BW); I2=BW; originalmap=I2; %calculate every pixel's IV(Interest value) %divide image I by w*w w=5;%divide to m*n m=floor(size(I2,1)/w); %rows，round n=floor(size(I2,2)/w); %columns %get the coordinate of every centroid c=ceil(w/2)+(0:n-1)*w; %x coordinate r=ceil(w/2)+(0:m-1)*w; %y coordinate %calculate every pixel's IV step=floor(w/2); for y_unit=1:m for x_unit=1:n %计算横向相邻像素灰度差的平方和 v1=0;v2=0;v3=0;v4=0; for i=-step:step-1 %计算横向相邻像素灰度差的平方和 v1=v1+(I2(r(y_unit),c(x_unit)+i)-I2(r(y_unit),c(x_unit)+i+1))^2; %计算右斜线方向相邻像素灰度差的平方和 v2=v2+(I2(r(y_unit)+i,c(x_unit)+i)-I2(r(y_unit)+i+1,c(x_unit)+i+1))^2; %计算纵向相邻像素灰度差的平方和 v3=v3+(I2(r(y_unit)+i,c(x_unit))-I2(r(y_unit)+i+1,c(x_unit)))^2; %计算左斜线方向相邻像素灰度差的平方和 v4=v4+(I2(r(y_unit)-i,c(x_unit)+i)-I2(r(y_unit)-i-1,c(x_unit)+i+1))^2; end %the min[v1,v2,v3,v4] is the IV of (c,r) IV_cr(y_unit,x_unit)=min([v1,v2,v3,v4]); end end %introduce a threshold 给定一个经验阈值。阈值的选取应以候选点包含所需要的特征点，而又不包含过多的非特征点为原则. exper_thr=1;IV_cr(IV_cr<exper_thr)=NaN; %remove the value less then threshold %选择候选点的极值点为特征点 %choose the size of window选择计算窗口大小 wf=9; %divide the feature points对候选点进行分割,分割为mf*nf个区域 mf=floor(m/wf); %rows nf=floor(n/wf); %columns %gain the coordinate of the feature point得到特征点的坐标 xc=[]; yc=[]; for y_unit=1:mf for x_unit=1:nf %计算分割区域中的最大值 [C,I2]=max(IV_cr((y_unit-1)*wf+1:y_unit*wf,(x_unit-1)*wf+1:x_unit*wf));%得到行 [C1,im]=max(C);%得到列 IV_crch(y_unit,x_unit)=C1; %得到分割区域中的最大值 row=I2(im); col=im; crch_row(y_unit,x_unit)=(y_unit-1)*wf+row; %得到最大值在候选区域中的行数 crch_col(y_unit,x_unit)=(x_unit-1)*wf+col; %得到最大值在候选区域中的列数 yc=[yc,r((y_unit-1)*wf+row)];xc=[xc,c((x_unit-1)*wf+col)]; IV_cr((y_unit-1)*wf+1:y_unit*wf,(x_unit-1)*wf+1:x_unit*wf)=NaN; %先去掉所有的点 IV_cr((y_unit-1)*wf+row,(x_unit-1)*wf+col)=C1; %加上符合要求的候选点 end end %先给出原来的图像 figure(2) imshow(originalmap) title('灰度化original image') xlabel('Horizontal') ylabel('Vertical') axis on %show the feature points图像中显示特征点 figure(3) imshow(originalmap) hold on plot(xc,yc,'R*') axis on title('feature points in the image') xlabel('the columns of the image') ylabel('the rows of the image')